在Pandas Dataframe中查找相似行并减去特定列值

import pandas as pd
from sklearn.metrics.pairwise import cosine_similarity

data = {'A': [1, 2, 3, 4, 5],
        'B': [2, 4, 6, 8, 10],
        'C': [3, 6, 9, 12, 15]}
df = pd.DataFrame(data)

similarity_matrix = cosine_similarity(df)

def subtract_similar_rows(df, similarity_matrix, row_index, column_to_subtract):
    similar_rows = similarity_matrix[row_index].argsort()[:-1]
    for similar_row in similar_rows:
        df.loc[similar_row, column_to_subtract] -= df.loc[row_index, column_to_subtract]

row_index = 0  # 要查找相似行的索引
column_to_subtract = 'C'  # 要减去的特定列
subtract_similar_rows(df, similarity_matrix, row_index, column_to_subtract)